Neural Bandit with Arm Group Graph

Abstract

Contextual bandits aim to identify among a set of arms the optimal one with the highest reward based on their contextual information. Motivated by the fact that the arms usually exhibit group behaviors and the mutual impacts exist among groups, we introduce a new model, Arm Group Graph (AGG), where the nodes represent the groups of arms and the weighted edges formulate the correlations among groups. To leverage the rich information in AGG, we propose a bandit algorithm, AGG-UCB, where the neural networks are designed to estimate rewards, and we propose to utilize graph neural networks (GNN) to learn the representations of arm groups with correlations. To solve the exploitation-exploration dilemma in bandits, we derive a new upper confidence bound (UCB) built on neural networks (exploitation) for exploration. Furthermore, we prove that AGG-UCB can achieve a near-optimal regret bound with over-parameterized neural networks, and provide the convergence analysis of GNN with fully-connected layers which may be of independent interest. In the end, we conduct extensive experiments against state-of-the-art baselines on multiple public data sets, showing the effectiveness of the proposed algorithm.

arXiv commentAccepted to SIGKDD 2022

References in corpus (20)

• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• A Convergence Theory for Deep Learning via Over-Parameterization
• Predict then Propagate: Graph Neural Networks meet Personalized PageRank
• Gradient Descent Finds Global Minima of Deep Neural Networks
• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
• Finite-Time Analysis of Kernelised Contextual Bandits
• Online Clustering of Bandits
• Neural Contextual Bandits with UCB-based Exploration
• Neural Thompson Sampling
• Multi-Task Learning for Contextual Bandits
• Optimization of Graph Neural Networks: Implicit Acceleration by Skip Connections and More Depth
• EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
• From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems
• Online Semi-Supervised Learning with Bandit Feedback
• Multi-facet Contextual Bandits: A Neural Network Perspective
• Contextual Bandit Applications in Customer Support Bot
• Neural Collaborative Filtering Bandits via Meta Learning

Cited by in corpus (1)

• Graph Neural Bandits